量化形状图复杂度，用拐点数预测用户认知负荷。
Quantifying Visual Properties of GAM Shape Plots: Impact on Perceived Cognitive Load and Interpretability
- 以拐点数量衡量形状图视觉复杂度
- 拐点数可解释86.4%的认知负荷差异
- 为模型可解释性评估提供无需用户测试的工具
广义加性模型（GAM）在性能与可解释性之间取得平衡，其可解释性通过形状图展现。然而，形状图的视觉属性（如拐点数量，即局部极大极小点个数）会影响其复杂度及观者的认知负荷，从而削弱可解释性。本研究包含57名参与者，分析144张形状图，量化其视觉属性并与用户感知的认知负荷进行对比。结果表明，拐点数量是最佳预测指标，能解释86.4%的用户评分方差。基于此构建的简单模型，可无需用户参与即评估模型某方面可解释性。
原文摘要 · Abstract (English)
Generalized Additive Models (GAMs) offer a balance between performance and interpretability in machine learning. The interpretability aspect of GAMs is expressed through shape plots, representing the model's decision-making process. However, the visual properties of these plots, e.g. number of kinks (number of local maxima and minima), can impact their complexity and the cognitive load imposed on the viewer, compromising interpretability. Our study, including 57 participants, investigates the relationship between the visual properties of GAM shape plots and cognitive load they induce. We quantify various visual properties of shape plots and evaluate their alignment with participants' perceived cognitive load, based on 144 plots. Our results indicate that the number of kinks metric is the most effective, explaining 86.4% of the variance in users' ratings. We develop a simple model based on number of kinks that provides a practical tool for predicting cognitive load, enabling the assessment of one aspect of GAM interpretability without direct user involvement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。